Method for analyzing correlation between urban space three-dimensional structure and population flow

Abstract

The invention discloses a town space three-dimensional structure and population flow correlation analysis method, and relates to the field of town space and population flow correlation analysis, and the method comprises the following steps: constructing a town construction index system based on a town construction data set, and carrying out the structural feature analysis of the town construction index system, urban construction three-dimensional space structure features are obtained; the method comprises the following steps: acquiring mobile phone signaling data by using a base station, identifying commuting behaviors of urban population, and constructing network structure characteristics of urban population flow; and constructing and training a regression model by using a LightGBM algorithm, and carrying out interpretive analysis on the regression model through an SHAP algorithm. According to the method, the importance degree of each feature of the urban spatial structure to population flow is explored by analyzing the spatial-temporal correlation between the urban spatial features and the population flow, and thus valuable reference is provided for the urban development planning direction by effectively utilizing the population flow trend.

Description

Technical Field

[0001] The present invention relates to the field of correlation analysis between urban space and population flow, and in particular to a method for correlation analysis between three-dimensional urban space structure and population flow. Background Art

[0002] At present, my country's urbanization is developing rapidly. Population mobility is an important carrier of information flow, logistics, capital flow, technology flow, etc. between regions. The large-scale flow of population between cities will greatly impact the industrial structure, transportation connection, infrastructure, employment situation, urban scale and other factors of the inflow and outflow areas, thereby triggering the reorganization of internal factors of cities, and causing a certain degree of change in the urban system structure and social development pattern. On the one hand, human activities promote the emergence and decline, expansion and contraction, prosperity and decline of cities, and dominate the production and life, technological innovation and knowledge iteration in cities; on the other hand, human activities occur within the spatial organizational framework of cities, which plays a role in constraining human activities. Therefore, in-depth identification of the laws of population flow direction, scale, network structure, etc., combined with geographical environment, socio-economic, historical and other factors, to explore the status of human activities and urban system construction in different regions can enrich the theoretical system and methods of population urban planning and population geography, and can provide reference basis and ideas for planning and coordinating future population flow patterns and promoting the healthy and stable development of inflow and outflow areas.

[0003] At present, the research on urban space and population mobility mainly focuses on the following aspects: First, by analyzing the direction, scale and network structure of population mobility, and combining factors such as geographical environment and socio-economic background, the characteristics of human activities in different regions and their impact on the urban system are explored; second, based on the characteristics of human flow activities or from the perspective of human flow, the network system composed of people's activities in the city is used to reflect the spatial distribution of activity centers and the relationship between centers, so as to reveal the essential characteristics of urban spatial structure; third, some studies map the urban spatial structure and function through the behavioral patterns of residents' travel, such as establishing a system dynamics model to measure the impact of urban spatial density, traffic conditions, economic conditions, etc. on residents' travel costs; in addition, some scholars use big data technology, such as mobile phone positioning data and trajectory data, to characterize the spatiotemporal characteristics of individual travel, explore its interaction with urban grids and urban functional structures, and further deepen the understanding of the characteristics of urban spatial structure.

[0004] Although current research has relatively comprehensively covered multiple dimensions of urban spatial structure and emphasized the impact of population distribution, density and human flow on urban structure, there are still deficiencies in the in-depth analysis of the specific relationship between urban spatial structure and population mobility. It is impossible to fully reveal the characteristics of population distribution through urban spatial layout, nor is it possible to effectively use population mobility trends to make precise adjustments to urban development plans.

[0005] Currently, no effective solution has been proposed for the problems in the related technologies. Summary of the invention

[0006] In view of the problems in the related technology, the present invention proposes a correlation analysis method between the three-dimensional structure of urban space and population flow to overcome the above-mentioned technical problems existing in the existing related technology.

[0007] To this end, the specific technical solution adopted by the present invention is as follows:

[0008] A correlation analysis method between a three-dimensional urban spatial structure and population mobility, the correlation analysis method comprising the following steps:

[0009] S1. Construct an urban construction index system based on the urban construction data set, and obtain the three-dimensional spatial structural characteristics of urban construction by analyzing the structural characteristics of the urban construction index system;

[0010] S2. Use base stations to obtain mobile phone signaling data and identify the commuting behavior of urban populations, and combine GIS spatial analysis methods to analyze and construct the network structure characteristics of urban population mobility;

[0011] S3. Use the three-dimensional spatial structure characteristics of urban construction and the network structure characteristics of urban population flow to construct a data set, and use the LightGBM algorithm to build and train a regression model. Use the SHAP algorithm to perform an interpretative analysis of the regression model to obtain the results of the correlation analysis between the three-dimensional spatial structure of towns and population flow.

[0012] Furthermore, the town construction index system is constructed based on the town construction data set. By analyzing the structural characteristics of the town construction index system, the three-dimensional spatial structural characteristics of town construction are obtained, which includes the following steps:

[0013] S11. Collect parameters of urban buildings to construct an urban construction data set, and analyze the distribution index of urban buildings and the suitability index of urban construction through statistical analysis method;

[0014] S12. Based on the distribution index of urban buildings, the structural characteristics of urban buildings are constructed through index calculation;

[0015] S13. Based on the urban construction suitability index, the urban construction suitability characteristics are calculated by expert scoring method and entropy weight method;

[0016] S14. Combine the town building structure characteristics and the town construction suitability characteristics to obtain the three-dimensional spatial structure characteristics of the town construction.

[0017] Furthermore, the characteristics of urban building structure include weighted average building height, building volume ratio, building coverage ratio, building volume, proportion of high-rise buildings and standard deviation of building height.

[0018] Furthermore, the formula for calculating the weighted average height of buildings is:

[0019]

[0020] In the formula, BH represents the weighted average height of the building, A i represents the area occupied by the base of building i, H i represents the height information of the i-th building, and n represents the sum of the number of areas belonging to the building;

[0021] The calculation formula for building volume ratio is:

[0022]

[0023] In the formula, BPR represents the building volume ratio, A i represents the area occupied by the base of building i, L i represents the number of floors of building i, n represents the sum of the number of areas belonging to the building, P a is the area of ​​the regional plot;

[0024] The calculation formula for building coverage is:

[0025]

[0026] In the formula, BC represents the building coverage rate, A i represents the area occupied by the base of building i, n represents the sum of the number of areas belonging to the building, P a Indicates the area of ​​the regional plot;

[0027] The formula for calculating the building volume is:

[0028]

[0029] Where BV represents the building volume, A i represents the area occupied by the base of building i, H i represents the height data of building i, and n represents the sum of the number of areas belonging to the building;

[0030] The formula for calculating the proportion of high-rise buildings is:

[0031]

[0032] In the formula, HBR represents the proportion of high-rise buildings, N g represents the number of high-rise buildings, and N represents the total number of buildings in the area;

[0033] The formula for calculating the standard deviation of building height is:

[0034]

[0035] Where BHSD represents the standard deviation of building height, H i represents the height information of the i-th building, μ represents the average height of the buildings, and N represents the total number of buildings in the area.

[0036] Furthermore, based on the urban construction suitability index, the calculation of urban construction suitability characteristics through expert scoring method and entropy weight method includes the following steps:

[0037] S131. normalizing each urban construction suitability index based on a normalization method to obtain a normalized index;

[0038] S132, performing quantization processing on the obtained normalized index to obtain a quantized index;

[0039] S133. Combine the expert scoring method and entropy weight method to conduct weight analysis on each quantitative indicator. According to the weight analysis results, use the weighted summation method to calculate the comprehensive score of each quantitative indicator, and use the comprehensive score as the suitability feature of urban construction.

[0040] Furthermore, using base stations to obtain mobile phone signaling data and identify the commuting behavior of urban populations, combined with GIS spatial analysis methods to analyze and construct the network structure characteristics of urban population mobility includes the following steps:

[0041] S21, using the base station to obtain the mobile phone signaling data of the urban population, and pre-processing the mobile phone signaling data;

[0042] S22, identifying the commuting behavior of the urban population by analyzing the commuting data between the residence and the workplace during the morning peak period and the evening peak period based on the pre-processed mobile phone signaling data;

[0043] S23, based on the commuting behavior of the urban population, calculating the commuting volume of the urban population in a preset time period;

[0044] S24, constructing a population flow network diagram of the town by taking the building locations in the town as nodes, the commuting behavior of the town population as edges, and the commuting volume of the town population in a preset time period as the weight attribute of the edges;

[0045] S25. Use Gephi layout algorithm to analyze the population flow network diagram of the town and obtain the network structure characteristics of the urban population flow.

[0046] Furthermore, preprocessing includes invalid and redundant data elimination, ping-pong data processing and drift data processing.

[0047] Furthermore, the three-dimensional spatial structure characteristics of urban construction and the network structure characteristics of urban population flow are used to construct a data set, and the LightGBM algorithm is used to build and train a regression model. The SHAP algorithm is used to interpret the regression model, and the results of the correlation analysis between the three-dimensional spatial structure of towns and population flow are obtained, including the following steps:

[0048] S31, divide the data set into training set and test set, use LightGBM algorithm to build a regression model and initialize model parameters;

[0049] S32, based on the initialization model parameters, using the training set to perform model training on the regression model, and adjusting and optimizing the model parameters through cross-validation;

[0050] S33, using the test set to evaluate the effect of the regression model, and calculating the performance evaluation index data of the model to obtain the evaluation result of the regression model;

[0051] S34. Use the SHAP algorithm to analyze the feature importance and influence direction of the evaluated regression model, and establish a SHAP summary diagram based on the analysis results;

[0052] S35. According to the summary diagram of SHAP, the correlation between the three-dimensional spatial structure of towns and population mobility is analyzed to obtain the correlation analysis results.

[0053] Furthermore, the performance evaluation index data of the model include the coefficient of determination, mean absolute error, mean absolute percentage error and root mean square error.

[0054] Furthermore, the SHAP algorithm is used to analyze the feature importance and influence direction of the evaluated regression model. The following steps are included to establish a SHAP summary diagram based on the analysis results:

[0055] S341. Based on the principle of cooperative game theory, the Shapley value is calculated using the evaluated regression model;

[0056] S342. Based on the Shapley value, the influence degree of the characteristic variables and the direction of the characteristic action are interpreted and visualized, and the SHAP model is used to draw a visual chart to obtain a SHAP summary chart.

[0057] The beneficial effects of the present invention are:

[0058] 1. The present invention ensures that the essential characteristics of the urban spatial structure are accurately grasped by analyzing the three-dimensional characteristics of the urban spatial structure. At the same time, by analyzing the network characteristics of population flow, the distribution of urban population flow and the characteristics of human activities are grasped, and a basis is further provided for in-depth analysis of the relationship between urban spatial structure and population flow. Then, by analyzing the spatiotemporal correlation between urban spatial characteristics and population flow, the importance of various characteristics of urban spatial structure to population flow is explored, and then the population flow trend is effectively used to provide valuable reference for the direction of urban development planning.

[0059] 2. The present invention obtains the suitability of urban construction and six indicators based on the urban building height data set and various urban element indicators to analyze the three-dimensional characteristics of the urban spatial structure, so as to describe the architectural form, spatial distribution and urban development level of the town, and ensure the accurate grasp of the essential characteristics of the urban spatial structure.

[0060] 3. The present invention identifies the user's commuting behavior based on mobile phone signaling data, and then combines GIS spatial analysis methods to analyze and compare the network characteristics of population flow in various towns, grasp the distribution of population flow in towns and the characteristics of human activities, so as to understand the economic development trends, employment opportunities, urban planning, transportation facilities, economic activities between towns and the density of social exchanges in these regions, and further provide a basis for in-depth analysis of the relationship between urban spatial structure and population flow.

[0061] 4. Based on the LightGBM algorithm, the present invention takes the comprehensive suitability of urban construction and six indicators as input, and population flow as output to construct a model. According to the model research results, the SHAP algorithm is used to analyze the influence of various input characteristics on population flow, so as to explore the importance of various characteristics of urban spatial structure to population flow, accurately grasp the driving factors of population flow, further analyze the correlation between urban spatial characteristics and population flow, and effectively use the correlation results to provide valuable reference for the direction of urban development planning. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0063] Figure 1 is a flow chart of a correlation analysis method between a three-dimensional urban spatial structure and population mobility according to an embodiment of the present invention;

[0064] Figure 2It is a schematic diagram of calculating the weighted average height (BH) of buildings in a grid in a correlation analysis method between a three-dimensional urban space structure and population flow according to an embodiment of the present invention;

[0065] Figure 3 It is a schematic diagram of calculating the building volume ratio (BPR) in a grid in a correlation analysis method between a three-dimensional urban space structure and population flow according to an embodiment of the present invention;

[0066] Figure 4 It is a population flow network diagram in a method for analyzing the correlation between a three-dimensional urban spatial structure and population flow according to an embodiment of the present invention;

[0067] Figure 5 It is a SHAP scatter summary diagram of the LightGBM model in a correlation analysis method between a three-dimensional urban spatial structure and population flow according to an embodiment of the present invention;

[0068] Figure 6 It is a SHAP bar summary chart of the LightGBM model in a correlation analysis method between a three-dimensional urban spatial structure and population flow according to an embodiment of the present invention. DETAILED DESCRIPTION

[0069] To further illustrate each embodiment, the present invention provides drawings, which are part of the disclosure of the present invention and are mainly used to illustrate the embodiments. They can be used in conjunction with the relevant descriptions in the specification to explain the operating principles of the embodiments. With reference to these contents, ordinary technicians in this field should be able to understand other possible implementation methods and advantages of the present invention.

[0070] According to an embodiment of the present invention, a method for analyzing the correlation between the three-dimensional structure of urban space and population mobility is provided.

[0071] The present invention will now be further described with reference to the accompanying drawings and specific embodiments. Figure 1 As shown, according to the correlation analysis method between the three-dimensional structure of urban space and population flow in an embodiment of the present invention, the correlation analysis method includes the following steps:

[0072] S1. Construct an urban construction index system based on the urban construction data set, and obtain the three-dimensional spatial structural characteristics of urban construction by analyzing the structural characteristics of the urban construction index system;

[0073] Specifically, urban construction data sets include spatial survey data, earth observation big data, etc.

[0074] Spatial survey data: data from the national land survey (abbreviated as the "third survey"), which can be divided into six major types based on 12 primary categories, namely grassland, cultivated land, forest land, water area, construction land and unused land.

[0075] Geospatial Observation Big Data: Building height data, provided by the National Earth System Science Data Center. This dataset contains all buildings in China with a height exceeding 10 meters. Each building in the data includes its geographical coordinates, height information, building outline and other attributes. The building height data can be used to construct a three-dimensional feature index of the city, reflecting the characteristics of the urban spatial structure.

[0076] For example, according to the "2022 Fire Protection Code" and the "General Rules for the Design of Civil Buildings", the buildings in a certain southern province of China are divided into 4 categories, namely low-rise buildings (h <= 10m), mid-rise buildings (10m < h <= 24m), mid-high-rise buildings (24m < h <= 50m), and high-rise buildings (h > 50m). Following the above rules, based on the building height dataset, using the statistical analysis method of ArcGIS, the distribution profile of the number of buildings in different height ranges is studied, and the analysis results are shown in Table 1. It can be seen that the number of mid-rise buildings is the largest, accounting for 78.65%; followed by mid-high-rise buildings, accounting for 18.15%; the proportions of low-rise buildings and high-rise buildings are close, and the numbers are very small, accounting for 1.68% and 1.52% respectively.

[0077] Table 1 Number and Proportion of Buildings in Different Height Floors in a Certain Southern Province of China

[0078]

[0079]

[0080] Among them, six indicators are selected, namely Building Height, Building Plot Ratio, Building Coverage, Building Volume, High-rise Building Ratio, and Building Height Standard Deviation, to describe the three-dimensional structural characteristics of the urban space, so as to describe the building form, spatial distribution and urban development level of the city. At the same time, to ensure the homogenization of the evaluation unit, a 1000-meter grid is used as the basic evaluation unit, that is, the research area of a certain southern province of China is divided into 148,551 1000*1000m grids.

[0081] Specifically, based on the urban construction dataset, an urban construction index system is constructed. Through the structural characteristic analysis of the urban construction index system, the three-dimensional spatial structural characteristics of urban construction are obtained, including the following steps:

[0082] S11. Collect parameters of urban buildings to construct an urban construction data set, and analyze the distribution index of urban buildings and the suitability index of urban construction through statistical analysis method;

[0083] In addition, urban construction suitability is also one of the characteristics of urban structure. Urban construction suitability evaluation is an integration of urban land resources, water resources, environment, disasters, location and other factors. It conducts a comprehensive and detailed analysis of the specific conditions of various land uses and functional areas within the city, and has an insight into the current development status of the city, further clarifying the positioning, nature and development goals of the city.

[0084] S12. Based on the distribution index of urban buildings, the structural characteristics of urban buildings are constructed through index calculation;

[0085] Specifically, the characteristics of urban building structure include the weighted average height of buildings, building volume ratio, building coverage ratio, building volume, proportion of high-rise buildings and standard deviation of building height.

[0086] Among them, the weighted average height of buildings (BH): This index reflects the average height level of urban buildings and is used to characterize the height information of buildings and the vertical development level of the city. When this index is analyzed in grid units, the schematic diagram calculated in each grid is as follows Figure 2 shown.

[0087] Building volume (BV): This index represents the three-dimensional space occupied by buildings and reflects the scale of buildings and the level of building development in a city.

[0088] Building coverage (BC): This index represents the horizontal space occupied by buildings and reflects the building density and land use efficiency of the city.

[0089] Building Volume Ratio (BPR): This index reflects the ratio of the volume of urban buildings to the land area, which can characterize the density of horizontal building distribution and the intensity of vertical development. When this index is analyzed in grid units, the plot area is the grid area calculation diagram as shown below: Figure 3 shown.

[0090] High-rise Building Ratio (HBR): This index reflects the proportion of high-rise buildings in a city and can characterize the city's building structure. The index is calculated based on each district or county in the city.

[0091] Building Height Standard Deviation (BHSD): This index reflects the degree of dispersion of urban building heights and is used to characterize the distribution changes and architectural forms of urban building heights. The index is calculated based on each district or county in the city.

[0092] Specifically, the formula for calculating the weighted average height of buildings is:

[0093]

[0094] In the formula, BH represents the weighted average height of the building, A i represents the area occupied by the base of building i, H i represents the height information of the i-th building, and n represents the sum of the number of areas belonging to the building;

[0095] The calculation formula for building volume ratio is:

[0096]

[0097] In the formula, BPR represents the building volume ratio, A i represents the area occupied by the base of building i, L i represents the number of floors of building i, n represents the sum of the number of areas belonging to the building, P a is the area of ​​the regional plot;

[0098] The calculation formula for building coverage is:

[0099]

[0100] In the formula, BC represents the building coverage rate, A i represents the area occupied by the base of building i, n represents the sum of the number of areas belonging to the building, P a Indicates the area of ​​the regional plot;

[0101] The formula for calculating the building volume is:

[0102]

[0103] Where BV represents the building volume, A i represents the area occupied by the base of building i, H i represents the height data of building i, and n represents the sum of the number of areas belonging to the building;

[0104] The formula for calculating the proportion of high-rise buildings is:

[0105]

[0106] In the formula, HBR represents the proportion of high-rise buildings, N g represents the number of high-rise buildings (buildings with a height greater than 24m), and N represents the total number of buildings in the area;

[0107] The formula for calculating the standard deviation of building height is:

[0108]

[0109] Where BHSD represents the standard deviation of building height, Hi represents the height information of the i-th building, μ represents the average height of the buildings, and N represents the total number of buildings in the area.

[0110] S13. Based on the urban construction suitability index, the urban construction suitability characteristics are calculated by expert scoring method and entropy weight method;

[0111] Specifically, based on the urban construction suitability index, the calculation of urban construction suitability characteristics through expert scoring method and entropy weight method includes the following steps:

[0112] S131. normalizing each urban construction suitability index based on a normalization method to obtain a normalized index;

[0113] S132, performing quantization processing on the obtained normalized index to obtain a quantized index;

[0114] S133. Combine the expert scoring method and entropy weight method to conduct weight analysis on each quantitative indicator. According to the weight analysis results, use the weighted summation method to calculate the comprehensive score of each quantitative indicator, and use the comprehensive score as the suitability feature of urban construction.

[0115] S14. Combine the town building structure characteristics and the town construction suitability characteristics to obtain the three-dimensional spatial structure characteristics of the town construction.

[0116] S2. Use base stations to obtain mobile phone signaling data and identify the commuting behavior of urban populations, and combine GIS spatial analysis methods to analyze and construct the network structure characteristics of urban population mobility;

[0117] It should be noted that mobile phone signaling data is data automatically captured and recorded by the system when the user triggers a related communication event. As long as the mobile phone is turned on, it will continue to exchange signals with the communication base station. When the mobile phone user moves to different locations at different time points, the communication base station they are connected to will also change accordingly. Because each interaction records the current base station location information, mobile phone signaling data is generated. Each signaling data contains multiple key fields, covering core information such as the base station identification code, the location area code triggered by the signaling, and the signaling trigger time.

[0118] Specifically, using base stations to obtain mobile phone signaling data and identify the commuting behavior of urban populations, and combining GIS spatial analysis methods to analyze and construct the network structure characteristics of urban population mobility includes the following steps:

[0119] S21, using the base station to obtain the mobile phone signaling data of the urban population, and pre-processing the mobile phone signaling data;

[0120] Specifically, preprocessing includes invalid and redundant data elimination, ping-pong data processing and drift data processing.

[0121] Specifically, invalid and redundant data are eliminated. This data loss is due to problems such as poor network conditions, delays, and data transmission interruptions when the mobile device communicates with the base station, which will lead to the loss of base station information that records signaling data, including base station code, location area code (LAC), and base station latitude and longitude. Redundant data refers to the situation where the user triggers multiple repeated mobile phone signal data under the same base station, but in fact the mobile phone user has not made corresponding location changes. These invalid and redundant data will affect the accuracy and efficiency of subsequent data analysis, so they need to be filtered and cleaned in the data preprocessing stage to retain valid data samples. For missing data, the corresponding data is filtered and then deleted. For redundant data with complete and continuous base station information, it is processed by using the merge-add method, which adds the duration of communication between the mobile terminal and the base station and deletes the merged data.

[0122] Ping-pong data processing refers to the situation that a mobile device may encounter weak or unstable signals during communication, resulting in a decrease in the quality of the connection with the current base station. In order to maintain the stability of communication, the device will try to switch to other base stations; the mobile device may cross the coverage boundary of different base stations during movement. When the device moves to a new base station coverage area, it will try to establish a connection with the new base station, which will lead to frequent switching between base stations. When the mobile device repeatedly locates between different base stations, ping-pong data will be generated. For the ping-pong data switching phenomenon, there are two common cell coding sequences: ABCA and ABA. Based on the methods in existing research, it is first determined whether the cell coding sequence belongs to the ping-pong data switching type, and then the sequences that meet the conditions are merged. During the processing, the start time of the first signaling of the ping-pong data and the end time of the last signaling are updated to the corresponding fields of the new signaling, and the total duration of the repeated data is accumulated and recorded as the actual stay time of the new signaling data at the base station.

[0123] Drift data processing refers to the phenomenon that the location of a mobile device remains unchanged or changes slowly over a period of time, but the data is offset or drifted due to factors such as error accumulation or environmental changes. For example, when a mobile device is operating for a long period of time, the sensor may change due to external environmental factors such as temperature fluctuations, humidity changes or external pressure, resulting in the gradual accumulation of errors in data output, thereby causing the drift of location data. At the same time, positioning system errors, algorithm errors, signal interference, etc. may introduce drift in the data processing process, affecting the accuracy of location data. Based on existing research, first screen whether the spatial distance between mobile phone base stations recorded in signaling data exceeds a certain threshold, and in order to identify drift data, the first task is to evaluate whether the switching speed exceeds the normal range; then integrate adjacent drift records, and update the start time of the merged data to the start time of the previous signaling, and the end time to the end time of the next signaling, and add up the duration of the integrated drift records, which is recorded as the base station stay duration of the new signaling data.

[0124] S22, identifying the commuting behavior of the urban population by analyzing the commuting data between the residence and the workplace during the morning peak period and the evening peak period based on the pre-processed mobile phone signaling data;

[0125] S23, based on the commuting behavior of the urban population, calculating the commuting volume of the urban population in a preset time period;

[0126] For example, to analyze personnel mobility, we must first determine the residence and workplace of the user object. This article uses each natural month as the statistical unit. There are many stopover points in the user's monthly trajectory, and it is necessary to find the user's residence and workplace among these points. The general working time period is between 7 am and 7 pm. Since nighttime activities after get off work vary from person to person, some users may not return directly to their place of residence. The rest time is defined as from 11 pm to 7 am the next day. The present invention defines the place where the longest stay is from 11 pm to 7 am in a month (and the number of days of stay exceeds 15 days) as the residence of the signaling user; the place where the longest stay is from 7 am to 7 pm in a month (and the number of days of stay exceeds 10 days) is defined as the workplace of the signaling user.

[0127] First, we define the relevant concepts. The population mobility research of the present invention mainly focuses on commuting behavior between districts and counties. The definition of commuting behavior is that 6 am to 9 am and 5 pm to 9 pm on weekdays are regarded as employment commuting round-trip periods. If a signaling user moves from work to residence or residence to work during this period, it is defined as a commuting behavior. The number of commuters is the number obtained by deduplicating the signaling users who commuted based on their ID numbers. The monthly average number of commuters is obtained by adding up the daily number of commuters. The commuting volume is obtained by adding up single commuting behaviors and distinguishing according to the round-trip locations, that is, A to B and B to A are counted as two commuting behaviors. The monthly average commuting volume is obtained by adding up the daily commuting volume.

[0128] The specific calculation logic is to first read the signaling data from the base station, and filter out people whose work and residence do not overlap based on the work-residence identification. The signaling data of these users are analyzed. In order to find the commuting behavior, the screening time range is the employment commuting period. At the same time, according to the latitude and longitude information of the base station in the signaling data, the district and county to which they belong are located, and the administrative district information is added. According to the daily base station recording time sorting, the earliest time when the morning and evening peaks appear at the residence and the earliest time when they appear at the workplace are obtained, and the data of the residence and workplace during the morning and evening peaks are integrated. The earliest time when the morning peak appears at the residence is less than the earliest time when it appears at the workplace, and the earliest time when the evening peak appears at the workplace is less than the earliest time when it appears at the residence can be counted as one commuting behavior. Finally, according to this standard, according to the commuting work and residence grouping, the daily commuting volume is obtained, and the monthly commuting volume is accumulated; according to the user grouping, the number of single commuting can be obtained; according to the user ID number, the number of daily commuters is obtained, and the monthly commuting number is accumulated. At the same time, the user's age information can be obtained based on the user's ID card information, the user's age portrait can be read, and the number of people in each age group can be obtained by age grouping.

[0129] S24, constructing a population flow network diagram of the town by taking the building locations in the town as nodes, the commuting behavior of the town population as edges, and the commuting volume of the town population in a preset time period as the weight attribute of the edges;

[0130] S25. Use Gephi layout algorithm to analyze the population flow network diagram of the town and obtain the network structure characteristics of the urban population flow.

[0131] Specifically, the present invention uses complex network analysis, combined with GIS spatial analysis methods, to study the relationship between population flow directions and node scales between towns, analyze and compare the network characteristics of population flows in various towns, and from the perspective of connection, use population flows to analyze the characteristics of population travel in different regions, and explore their ability to attract and radiate human traffic.

[0132] The population flow network diagram was drawn using Gephi software (such as Figure 4 As shown), Gephi is an open source network visualization tool that can be used to analyze and visualize complex network data, help in-depth study of network structure, relationships and patterns, and intuitively display network data in a graphical way. First, make a node table and edge table input into Gephi. The node table contains the districts and counties of a province in southern my country, and supplements the longitude and latitude information of each town. When the Gephi layout algorithm is used to optimize the network structure and network diagram layout, geographic coordinate network visualization can be realized, and the nodes are classified by city level for subsequent visualization; the connection flow information flowing in and out between each region is input into the edge table, and the round-trip commuting volume of the population in a county in southern my country is used as the weight attribute of the edge to show the directionality and strength of the network. Gephi can perform various network analysis tasks, such as calculating the degree, betweenness, clustering coefficient and other indicators of the node, as well as detecting community structure, identifying important nodes in the network, etc. Here, the present invention first uses the weight of the edge to define the style of the edge. The larger the flow volume, the wider the width of the edge. In order to improve the visualization effect, the node size and the color of the nodes and edges are not set too much to avoid too much clutter in the figure. Here, only a certain province-level administrative region in southern my country is classified and visualized, and different colors represent different cities. From the figure, it can be seen that the population in the northeast and central regions flows back and forth frequently, and the connection between towns is strong, indicating that these regions have a good economic development trend, many employment opportunities, complete and convenient urban planning and transportation facilities, and intensive economic activities and social exchanges between towns, which attract a large number of population flows; other regions have weak connections and have not formed a core with strong population attraction and radiation, which means that the economic development level of these regions is relatively low, and the influence of the central area of ​​the town is not large enough to effectively mobilize the economic exchanges and exchanges of the town and absorb talents.

[0133] S3. A data set is constructed using the three-dimensional spatial structure characteristics of urban construction and the network structure characteristics of urban population flow. A regression model is constructed and trained using the LightGBM algorithm. The regression model is interpreted using the SHAP algorithm to obtain the results of the correlation analysis between the three-dimensional spatial structure of towns and population flow.

[0134] It should be noted that in order to capture the complex nonlinear interactions between variables, the present invention uses the LightGBM algorithm and the Shapley value interpretation model to further analyze the relationship between urban spatial characteristics and the spatiotemporal behavior of population mobility, to explain and visualize the effect of urban spatial factors on population mobility, and to explore the association mechanism therein.

[0135] LightGBM (GBDT, Gradient Boosting Decision Tree) refers to the gradient boosting decision tree algorithm, whose basic principle is to complete the prediction task by building an integration of multiple decision tree models. GBDT is an ensemble learning method that gradually reduces the training error by gradually building a decision tree model. In each round of iteration, GBDT learns a new decision tree model that attempts to capture the residuals of samples in the training data that were predicted incorrectly by the previous model, thereby gradually reducing the residuals and ultimately achieving the purpose of fitting the training data. The core principle of LightGBM is to optimize the speed and efficiency of the gradient boosting algorithm through the Leaf-wise growth strategy and the histogram algorithm. The Leaf-wise growth strategy means that in the splitting process, the leaf nodes that are most helpful to the current node are always split. This strategy can build more leaf nodes at the same depth and improve the accuracy of the model. The histogram algorithm first discretizes the continuous feature values ​​and divides them into different bins, and then uses the histogram to find the best split point at each split. This algorithm can reduce the amount of calculation and memory usage and improve the training speed of the model.

[0136] Model methods such as machine learning models, which have increasingly complex decisions and opaque decision-making processes, have increasingly low interpretability. According to the proposed SHAP as an explanatory indicator of feature value in the model, this is an additive feature attribution method with local and global explanatory power. This concept first appeared in game theory and was used to measure the value of each party in the game process. In machine learning models, the various feature variables of a sample can be regarded as participants in the game process, and the Shapley value of the feature reflects the contribution of this feature to the model results. The calculation principle of the Shapley value is based on the concept in cooperative game theory, which measures the contribution of each feature to the model prediction results.

[0137] Specifically, the three-dimensional spatial structure characteristics of urban construction and the network structure characteristics of urban population flow are used to construct a data set, and the LightGBM algorithm is used to build and train a regression model. The SHAP algorithm is used to interpret the regression model. The results of the correlation analysis between the three-dimensional spatial structure of towns and population flow are obtained, which include the following steps:

[0138] S31, divide the data set into training set and test set, use LightGBM algorithm to build a regression model and initialize model parameters;

[0139] S32, based on the initialization model parameters, using the training set to perform model training on the regression model, and adjusting and optimizing the model parameters through cross-validation;

[0140] S33, using the test set to evaluate the effect of the regression model, and calculating the performance evaluation index data of the model to obtain the evaluation result of the regression model;

[0141] It should be noted that, based on the LightGBM algorithm, the present invention takes the variable factors of urban spatial structure (three-dimensional spatial structure characteristics of urban construction) as input, and population flow (network structure characteristics of urban population flow) as output to construct a data set. 85% of them are randomly selected as training sets and 15% as test sets to build a model. The model parameters are set, including the number of training base learners, the maximum leaf nodes of each base learner, the learning rate, the depth of the tree, the number of iterations and other parameters. After cross-validation and continuous adjustment and optimization of the parameters, the accuracy of the model is further improved. Finally, the parameters are set to 70, 50, 0.01, 6, and 10000 respectively. After setting the parameters, the model is trained, and the effect of the model is evaluated in combination with the test set. The present invention selects the coefficient of determination (R 2 ), mean absolute error (MAE), mean absolute percentage error (MAPE), and root mean square error (RMSE) are used as indicators to verify the accuracy of the model.

[0142] Read data and set parameters in R language, build and train the regression model of LightGBM algorithm, obtain the fitted scatter plot, and calculate R 2 The coefficient of determination of the model is close to 1, indicating that the model can well explain the changes of the target variable. At the same time, the other three error values ​​are relatively small, indicating that the prediction error of the model is small and the fitting effect is good. The fitting results show that the influencing factor system selected by the present invention is reasonable and has a strong explanatory power for the dependent variable.

[0143] S34. Use the SHAP algorithm to analyze the feature importance and influence direction of the evaluated regression model, and establish a SHAP summary diagram based on the analysis results;

[0144] Specifically, the performance evaluation index data of the model include the coefficient of determination, mean absolute error, mean absolute percentage error and root mean square error.

[0145] Specifically, the SHAP algorithm is used to analyze the feature importance and influence direction of the evaluated regression model. The following steps are included to establish a SHAP summary diagram based on the analysis results:

[0146] S341. Based on the principle of cooperative game theory, the Shapley value is calculated using the evaluated regression model;

[0147] S342. Based on the Shapley value, the influence degree of the characteristic variables and the direction of the characteristic action are interpreted and visualized, and the SHAP model is used to draw a visual chart to obtain a SHAP summary chart.

[0148] S35. According to the summary diagram of SHAP, the correlation between the three-dimensional spatial structure of towns and population mobility is analyzed to obtain the correlation analysis results.

[0149] It should be noted that there are two forms of SHAP summary graphs: one is a scatter plot showing the individual features of all samples, and the other is a bar graph based on the absolute mean of the Shapley value of each feature to reflect the importance of the feature. The importance of a feature indicates the degree of reference dependence on the feature in model prediction. Generating a SHAP summary graph can not only determine the importance ranking of all features, but also analyze the positive or negative impact of each feature's Shapley value on the prediction results, so as to better understand the contribution of different features in model prediction.

[0150] like Figure 5 As shown in the figure (the dot represents each sample point, the color of the dot represents the eigenvalue corresponding to the sample point, the closer the color is to the light color, the higher the eigenvalue, and the closer the color is to the dark color, the lower the eigenvalue). It is a SHAP scatter plot. The vertical axis represents the influencing factors, that is, the characteristics of each independent variable. They are arranged from top to bottom according to the importance of the feature in the model. It can be seen that the top three are building coverage (BC), high-rise building ratio (HBR), and urban construction suitability (ConsS). The horizontal axis is the Shapley value of each feature, that is, the weight of each variable on the dependent variable. If it is greater than 0, it means that it has a positive promoting effect on population mobility, and if it is less than 0, it means that it has a reverse inhibitory effect. At the same time, the larger the absolute value of the value, the deeper the degree of influence. The scatter plot corresponding to each feature in each row of the figure represents the impact of the feature, in which each point is a sample, and the color of the point represents the level of the eigenvalue of each sample. The closer the color is to the light color, the higher the eigenvalue, and the closer the color is to the dark color, the lower the eigenvalue.

[0151] exist Figure 5It can be observed that the top three features have similar effects on population mobility. The sample points with SHAP values ​​less than 0 are mainly close to dark colors, and the sample points with SHAP values ​​greater than 0 are generally light colors, which means that the higher the values ​​of these features, the more they can promote population mobility, and vice versa. However, it can be clearly seen that the samples of building coverage (BC) are more dispersed, and the points of high-rise building proportion (HBR) and urban construction suitability (ConsS) are more dense and concentrated around the SHAP value of zero, indicating that the higher the values ​​of these two features, the more they promote population mobility, which is not as obvious as the building coverage (BC). The influence of the remaining four characteristics is more complicated. The sample points with high characteristic values ​​of the weighted average height of buildings (BH) are distributed around the SHAP zero value, and the distribution is roughly uniform. At the same time, some sample points with low characteristic values ​​are distributed in the SHAP negative value area. This shows that the low weighted average height of buildings will have a certain inhibitory effect on population mobility, but the influence of the high weighted average height of buildings on population mobility is very complex and there is no obvious guiding pattern; most of the points with low characteristic values ​​of building volume (BH) are distributed in the positive SHAP value area and near the zero value, and there are low-value points scattered in the SHAP negative value area, indicating that the influence mechanism of this feature on population mobility is complex; a large number of light-colored (high-value) sample points of the building height standard deviation (BHSD) are concentrated around the SHAP zero value, indicating that this feature has no significant effect on the dependent variable. Similarly, the building volume ratio (BPR) shows that all sample points are concentrated at the SHAP zero value, indicating that the volume ratio has almost no effect on population mobility in this model.

[0152] like Figure 6 As shown in the figure, it is another summary chart of the SHAP bar chart. The vertical axis represents the various features input into the model, and the horizontal axis represents the mean of the absolute value of the SHAP of each feature, which quantifies the influence of the feature on the overall prediction of the model. Like the scatter plot, the features are arranged from top to bottom according to their importance in the model, but unlike the scatter plot, the bar chart can reflect the relative importance of the features instead of just the ranking. Figure 6 Although the high-rise building ratio (HBR) and urban construction suitability (ConsS) ranked second and third, their importance was very close, and both were only about half of the first-place building coverage rate (BC); in addition, it was observed that the building volume ratio (BPR) not only ranked last, but its importance was almost zero.

[0153] In summary, based on the analysis results of LightGBM and SHAP, it can be seen that among all the characteristics, the building coverage rate (BC), the proportion of high-rise buildings (HBR), and the suitability of urban construction (ConsS) are the most important. The higher their characteristic values, the more they can promote population mobility. Among them, the importance of building coverage rate is twice that of the second feature, and it has the greatest impact on the flow of people. Therefore, the spatial structure system is also a driving factor for the characteristics of the floating population.

[0154] In summary, with the help of the above technical solutions of the present invention, the present invention ensures that the essential characteristics of the urban spatial structure are accurately grasped by analyzing the three-dimensional characteristics of the urban spatial structure, and at the same time, by analyzing the network characteristics of population flow, grasps the distribution of urban population flow and the characteristics of human activities, and further provides a basis for in-depth analysis of the relationship between urban spatial structure and population flow, and then explores the importance of various characteristics of urban spatial structure to population flow through the analysis of the spatiotemporal correlation between urban spatial characteristics and population flow, and then effectively uses the population flow trend to provide valuable reference for the direction of urban development planning. The present invention analyzes the three-dimensional characteristics of the urban spatial structure by obtaining the suitability of urban construction and six indicators based on the urban building height data set and various urban element indicators, so as to describe the architectural form, spatial distribution and urban development level of the town, and ensure the accurate grasp of the essential characteristics of the urban spatial structure. The present invention identifies the commuting behavior of users based on mobile phone signaling data, and then combines GIS spatial analysis methods to analyze and compare the network characteristics of population mobility in various towns, grasp the distribution of population mobility in towns and the characteristics of human activities, so as to understand the economic development trends, employment opportunities, urban planning, transportation facilities, economic activities between towns and the density of social exchanges in these regions, and further provide a basis for in-depth analysis of the relationship between urban spatial structure and population mobility. Based on the LightGBM algorithm, the present invention takes the comprehensive suitability of urban construction and six indicators as input, and population mobility as output to construct a model. According to the model research results, the SHAP algorithm is used to analyze the influence of various input characteristics on population mobility, so as to explore the importance of various characteristics of urban spatial structure to population mobility, accurately grasp the driving factors of population mobility, further analyze the correlation between urban spatial characteristics and population mobility, and effectively use the correlation results to provide valuable reference for the direction of urban development planning.

[0155] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for analyzing the correlation between urban spatial three-dimensional structure and population mobility, characterized in that: The correlation analysis method comprises the following steps: S1. Construct an urban construction index system based on the urban construction data set, and obtain the three-dimensional spatial structural characteristics of urban construction by analyzing the structural characteristics of the urban construction index system; S2. Use base stations to obtain mobile phone signaling data and identify the commuting behavior of urban populations, and combine GIS spatial analysis methods to analyze and construct the network structure characteristics of urban population mobility; S3. Use the three-dimensional spatial structure characteristics of urban construction and the network structure characteristics of urban population flow to construct a data set, and use the LightGBM algorithm to build and train a regression model. Use the SHAP algorithm to perform an interpretative analysis of the regression model to obtain the results of the correlation analysis between the three-dimensional spatial structure of towns and population flow.

2. The method for analyzing the correlation between the three-dimensional structure of urban space and population mobility according to claim 1, characterized in that: The construction of the town construction index system based on the town construction data set and obtaining the three-dimensional spatial structural characteristics of town construction by analyzing the structural characteristics of the town construction index system include the following steps: S11. Collect parameters of urban buildings to construct an urban construction data set, and analyze the distribution index of urban buildings and the suitability index of urban construction through statistical analysis method; S12. Based on the distribution index of urban buildings, the structural characteristics of urban buildings are constructed through index calculation; S13. Based on the urban construction suitability index, the urban construction suitability characteristics are calculated by expert scoring method and entropy weight method; S14. Combine the town building structure characteristics and the town construction suitability characteristics to obtain the three-dimensional spatial structure characteristics of the town construction.

3. The method for analyzing the correlation between the three-dimensional structure of urban space and population flow according to claim 2 is characterized in that: The urban building structure characteristics include the weighted average height of buildings, building volume ratio, building coverage ratio, building volume, proportion of high-rise buildings and standard deviation of building height.

4. The method for analyzing the correlation between the three-dimensional structure of urban space and population flow according to claim 2 is characterized in that: The calculation formula of the weighted average height of the building is: In the formula, BH represents the weighted average height of the building, A i represents the area occupied by the base of building i, H i represents the height information of the i-th building, and n represents the sum of the number of areas belonging to the building; The calculation formula of the building volume ratio is: In the formula, BPR represents the building volume ratio, A i represents the area occupied by the base of building i, L i represents the number of floors of building i, n represents the sum of the number of areas belonging to the building, P a is the area of ​​the regional plot; The calculation formula of the building coverage rate is: In the formula, BC represents the building coverage rate, A i represents the area occupied by the base of building i, n represents the sum of the number of areas belonging to the building, P a Indicates the area of ​​the regional plot; The calculation formula of the building volume is: In the formula, BV represents the building volume, Ai represents the base area of ​​building i, and H i represents the height data of building i, and n represents the sum of the number of areas belonging to the building; The calculation formula for the proportion of high-rise buildings is: In the formula, HBR represents the proportion of high-rise buildings, N g represents the number of high-rise buildings, and N represents the total number of buildings in the area; The calculation formula for the standard deviation of building height is: Where BHSD represents the standard deviation of building height, H i represents the height information of the i-th building, μ represents the average height of the buildings, and N represents the total number of buildings in the area.

5. The method for analyzing the correlation between the three-dimensional structure of urban space and population flow according to claim 2, characterized in that: The method of calculating the suitability characteristics of urban construction based on the urban construction suitability index by using the expert scoring method and the entropy weight method includes the following steps: S131. normalizing each urban construction suitability index based on a normalization method to obtain a normalized index; S132, performing quantization processing on the obtained normalized index to obtain a quantized index; S133. Combine the expert scoring method and entropy weight method to conduct weight analysis on each quantitative indicator. According to the weight analysis results, use the weighted summation method to calculate the comprehensive score of each quantitative indicator, and use the comprehensive score as the suitability feature of urban construction.

6. The method for analyzing the correlation between the three-dimensional structure of urban space and population flow according to claim 2, characterized in that: The method of using base stations to obtain mobile phone signaling data and identify the commuting behavior of urban population, and combining GIS spatial analysis methods to analyze and construct the network structure characteristics of urban population flow includes the following steps: S21, using the base station to obtain the mobile phone signaling data of the urban population, and pre-processing the mobile phone signaling data; S22, identifying the commuting behavior of the urban population by analyzing the commuting data between the residence and the workplace during the morning peak period and the evening peak period based on the pre-processed mobile phone signaling data; S23, based on the commuting behavior of the urban population, calculating the commuting volume of the urban population in a preset time period; S24, constructing a population flow network diagram of the town by taking the building locations in the town as nodes, the commuting behavior of the town population as edges, and the commuting volume of the town population in a preset time period as the weight attribute of the edges; S25. Use Gephi layout algorithm to analyze the population flow network diagram of the town and obtain the network structure characteristics of the urban population flow.

7. The method for analyzing the correlation between the three-dimensional structure of urban space and population flow according to claim 6, characterized in that: The preprocessing includes invalid and redundant data elimination, ping-pong data processing and drift data processing.

8. The method for analyzing the correlation between the three-dimensional structure of urban space and population flow according to claim 1, characterized in that: The method of constructing a data set using the three-dimensional spatial structure characteristics of urban construction and the network structure characteristics of urban population flow, constructing and training a regression model using the LightGBM algorithm, and performing an interpretative analysis of the regression model using the SHAP algorithm to obtain the results of the correlation analysis between the three-dimensional spatial structure of the town and the population flow includes the following steps: S31, divide the data set into training set and test set, use LightGBM algorithm to build a regression model and initialize model parameters; S32, based on the initialization model parameters, using the training set to perform model training on the regression model, and adjusting and optimizing the model parameters through cross-validation; S33, using the test set to evaluate the effect of the regression model, and calculating the performance evaluation index data of the model to obtain the evaluation result of the regression model; S34. Use the SHAP algorithm to analyze the feature importance and influence direction of the evaluated regression model, and establish a SHAP summary diagram based on the analysis results; S35. According to the summary diagram of SHAP, the correlation between the three-dimensional spatial structure of towns and population mobility is analyzed to obtain the correlation analysis results.

9. The method for analyzing the correlation between the three-dimensional structure of urban space and population flow according to claim 8, characterized in that: The performance evaluation index data of the model include determination coefficient, mean absolute error, mean absolute percentage error and root mean square error.

10. The method for analyzing the correlation between the three-dimensional structure of urban space and population flow according to claim 9, characterized in that: The SHAP algorithm is used to analyze the feature importance and influence direction of the evaluated regression model, and the SHAP summary diagram is established according to the analysis results, including the following steps: S341. Based on the principle of cooperative game theory, the Shapley value is calculated using the evaluated regression model; S342. Based on the Shapley value, the influence degree of the characteristic variables and the direction of the characteristic action are interpreted and visualized, and the SHAP model is used to draw a visual chart to obtain a SHAP summary chart.

Images